Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model. (September 2020)

• Record Type: Journal Article
• Authors: Ye, Hao-Tong; Lo, Kai-Lin; Su, Shang-Yu; Chen, Yun-Nung
• Is Part Of: Computer speech & language. Volume 63(2020)
• Publication Date: 2020-09
• Subjects: Knowledge-grounded -- Response generation -- Variational model; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2020.101069
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A novel variational inference model generates diverse responses. The condition allows the model to include grounded knowledge for informativeness. The proposed method shows the improvement on the benchmark data. Graphical abstract: Abstract: End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific to each task and corpus. However, one of the fatal drawbacks in such approaches is that they are unable to generate informative utterances, so it limits their usage from some real-world conversational applications. In order to tackle this issue, this paper attempts to generate diverse and informative responses with a variational generation model, which contains a joint attention mechanism conditioning on the information from both dialogue contexts and extra knowledge. The experiments on benchmark DSTC7 data show that the proposed method generates responses with more grounded knowledge and improve the diversity of generated language.